|
{ |
|
"additional_special_tokens": [ |
|
"<special0>", |
|
"<special1>", |
|
"<special2>", |
|
"<special3>", |
|
"<special4>", |
|
"<special5>", |
|
"<special6>", |
|
"<special7>", |
|
"<special8>", |
|
"<special9>" |
|
], |
|
"bos_token": "<s>", |
|
"cls_token": "</s>", |
|
"do_lower_case": false, |
|
"do_lowercase": false, |
|
"do_lowercase_and_remove_accent": true, |
|
"id2lang": null, |
|
"lang2id": null, |
|
"mask_token": "<special1>", |
|
"model_max_length": 512, |
|
"name_or_path": "flaubert/flaubert_base_cased", |
|
"pad_token": "<pad>", |
|
"sep_token": "</s>", |
|
"special_tokens_map_file": null, |
|
"tokenizer_class": "FlaubertTokenizer", |
|
"unk_token": "<unk>" |
|
} |
|
|